© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 20-CLT-HP
    7. 71378
    Prev
    Next
    INDEX
    Explanations

    academic/technical text

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     pageContext
    -1.01
    PreferredItem
    -0.94
     дописавши
    -0.90
     AssemblyTitle
    -0.89
     mergeFrom
    -0.87
    Personendaten
    -0.85
    AsUp
    -0.82
    windowFixed
    -0.81
    Билгалдахарш
    -0.81
     kaarangay
    -0.81
    POSITIVE LOGITS
     story
    0.36
    -
    0.35
     godz
    0.33
     prí
    0.33
    ే
    0.32
     stø
    0.32
    orsz
    0.30
    External
    0.29
     stories
    0.29
    StringVar
    0.29
    Activations Density 0.001%

    No Known Activations